Quantifying capability gaps via information relaxation and deep reinforcement learning in infinite-horizon Markov decision processes: A military air battle management application

Authors

Joseph M. Liles IV, Air Force Institute of Technology
Matthew J. Robbins, Air Force Institute of TechnologyFollow
Brian J. Lunday, Air Force Institute of TechnologyFollow

Document Type

Article

Publication Date

7-23-2025

Abstract

Excerpt: This paper presents a novel application of information relaxation techniques to quantify upper bounds on solution quality in a complex, stochastic, and dynamic assignment problem in military air battle management. Information relaxation refers to relaxing the non-anticipativity constraints in a sequential decision-making problem that require a decision-maker to act only on currently available information. We introduce a temporal event horizon—–an adjustable window into future stochastic outcomes—–to explore the marginal value of information in shaping decision policies.

Comments

This is published by Taylor and Francis as a subscription-access article. It is accessible to subscribers through the DOI link below.

DOI

10.1080/01605682.2025.2528915

Source Publication

Journal of the Operational Research Society (ISSN 0160-5682, 1476-9360)

Recommended Citation

Liles, J. M., IV, Robbins, M. J., & Lunday, B. J. (2025). Quantifying capability gaps via information relaxation and deep reinforcement learning in infinite-horizon Markov decision processes: A military air battle management application. Journal of the Operational Research Society, 1–16. https://doi.org/10.1080/01605682.2025.2528915